All Projects → xiaochus → Visualizationcnn

xiaochus / Visualizationcnn

Licence: mit
Visualization CNN model by Keras.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Visualizationcnn

keras-deep-learning
Various implementations and projects on CNN, RNN, LSTM, GAN, etc
Stars: ✭ 22 (-64.52%)
Mutual labels:  cnn-keras
Cnn keras
CNN | Keras/PyTorch | CAPTCHA recognition(卷积神经网络、Keras/PyTorch框架、验证码识别)
Stars: ✭ 256 (+312.9%)
Mutual labels:  cnn-keras
Self Driving Toy Car
A self driving toy car using end-to-end learning
Stars: ✭ 494 (+696.77%)
Mutual labels:  cnn-keras
FaceEmotionClassifier
人脸识别与卡通化
Stars: ✭ 102 (+64.52%)
Mutual labels:  cnn-keras
tennis action recognition
Using deep learning to perform action recognition in the sport of tennis.
Stars: ✭ 17 (-72.58%)
Mutual labels:  cnn-keras
Personality Detection
Implementation of a hierarchical CNN based model to detect Big Five personality traits
Stars: ✭ 338 (+445.16%)
Mutual labels:  cnn-keras
CNN-Image-Classifier
A Simple Deep Neural Network to classify images made with Keras
Stars: ✭ 65 (+4.84%)
Mutual labels:  cnn-keras
Kaggle Web Traffic Time Series Forecasting
Solution to Kaggle - Web Traffic Time Series Forecasting
Stars: ✭ 29 (-53.23%)
Mutual labels:  cnn-keras
DLSS
Deep Learning Super Sampling with Deep Convolutional Generative Adversarial Networks.
Stars: ✭ 88 (+41.94%)
Mutual labels:  cnn-keras
Deep learning nlp
Keras, PyTorch, and NumPy Implementations of Deep Learning Architectures for NLP
Stars: ✭ 407 (+556.45%)
Mutual labels:  cnn-keras
CNNs-on-CHB-MIT
The project is about applying CNNs to EEG data from CHB-MIT to predict seizure
Stars: ✭ 40 (-35.48%)
Mutual labels:  cnn-keras
Deep-Learning-for-Expression-Recognition-in-Image-Sequences
The project uses state of the art deep learning on collected data for automatic analysis of emotions.
Stars: ✭ 26 (-58.06%)
Mutual labels:  cnn-keras
Thesemicolon
This repository contains Ipython notebooks and datasets for the data analytics youtube tutorials on The Semicolon.
Stars: ✭ 345 (+456.45%)
Mutual labels:  cnn-keras
wildflower-finder
Image classification of wildflowers using deep residual learning and convolutional neural nets
Stars: ✭ 25 (-59.68%)
Mutual labels:  cnn-keras
Simple Railway Captcha Solver
實作基於CNN的台鐵訂票驗證碼辨識以及透過模仿及資料增強的訓練集產生器 (Simple captcha solver based on CNN and a training set generator by imitating the style of captcha and data augmentation)
Stars: ✭ 643 (+937.1%)
Mutual labels:  cnn-keras
automatic-personality-prediction
[AAAI 2020] Modeling Personality with Attentive Networks and Contextual Embeddings
Stars: ✭ 43 (-30.65%)
Mutual labels:  cnn-keras
Resnetcam Keras
Keras implementation of a ResNet-CAM model
Stars: ✭ 269 (+333.87%)
Mutual labels:  cnn-keras
Street View House Numbers Svhn Detection And Classification Using Cnn
A 2-CNN pipeline to do both detection (using bounding box regression) and classification of numbers on SVHN dataset.
Stars: ✭ 46 (-25.81%)
Mutual labels:  cnn-keras
Dl Workshop Series
Material used for Deep Learning related workshops for Machine Learning Tokyo (MLT)
Stars: ✭ 857 (+1282.26%)
Mutual labels:  cnn-keras
Benchmarking Keras Pytorch
🔥 Reproducibly benchmarking Keras and PyTorch models
Stars: ✭ 346 (+458.06%)
Mutual labels:  cnn-keras

VisualizationCNN

Visualization CNN model by Keras.

Requirement

  • Python 3.6
  • Keras 2.2.2
  • Tensorflow-gpu 1.8.0
  • OpenCV 3.4

Support model

  • VGG16
  • VGG19
  • ResNet50
  • InceptionV3
  • Xception
  • MobileNet
  • DenseNet121

Visualization (VGG16 example)

Visualizing intermediate conv outputs conv_block1_conv1 conv_block2_conv2 conv_block3_conv3 conv_block3_conv3

Visualizing conv filters filter_block1_conv1 filter_block2_conv2 filter_block2_conv2 filter_block2_conv2

Visualizing heatmaps of class activation in an image heatmap

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].